METHODS FOR MONITORING AND ASSESSING STUDENT ACTIVITY BASED ON MULTIMODAL LEARNING ANALYTICS
Keywords:
multimodal learning analytics, learning analytics, data-driven pedagogy, digital education, student activity monitoring, assessment system, adaptive assessment, multimodal monitoring, educational analytics, individual approach, learning outcomes, engagement, pedagogical analysis.Abstract
This article addresses the development of a methodology for monitoring and assessing student activity based on multimodal learning analytics and evaluates its effectiveness. The study is conducted within a digital learning environment using a data-driven pedagogy approach, where student activity is analyzed through multiple data sources, including platform logs, test results, interactive tasks, and video engagement. A multimodal monitoring model is proposed, structured around the stages of “data collection – analysis – decision-making – feedback,” enabling real-time assessment and the identification of individual learning trajectories. Experimental results demonstrate the superiority of the multimodal approach over traditional assessment systems. The findings confirm that this methodology enhances student engagement, improves learning outcomes, and supports individualized learning processes.
References
1. Papamitsiou Z., Economides A. A. Learning analytics and educational data mining: A systematic review // Educational Technology & Society. – 2020. – Vol. 23, No. 4. – P. 49–63.
2. Roll I., Wylie R.Evolution of AI in education // International Journal of Artificial Intelligence in Education. – 2021. – Vol. 31, No. 1. – P. 1–8.
3. Gašević D., Dawson S., Siemens G.Learning analytics are about learning // TechTrends. – 2020. – Vol. 64, No. 6. – P. 743–750.
4. Khalil M., Ebner M.Learning analytics: Principles and constraints // Computers in Human Behavior Reports. – 2022. – Vol. 5. – Art. 100144.
5. Matcha W., Uzir N. A., Gašević D., Pardo A.Learning analytics dashboards: A review // IEEE Transactions on Learning Technologies. – 2020. – Vol. 13, No. 2. – P. 1–15.
6. Chen B., Knight S., Wise A. F.Critical perspectives on learning analytics // British Journal of Educational Technology. – 2023. – Vol. 54, No. 2. – P. 1–19.
7. Pozilova Sh. Kh., Mirsalieva M. T., Kayumov O. A.Development of professional creativity of professional teachers in professional courses on the basis of e-pedagogy principle // Proceedings of ACM. – P. 66–71.
8. Kayumova N. R.Development of a methodological model and technological solutions for the software architecture of an inclusive and flexible learning platform // International Journal of Pedagogics. – 2025. – P. 116–121.
9. Kayumova N. R.Developing a functional model for effective education based on adaptive content, personalization, inclusive interface, and feedback mechanisms // European International Journal of Pedagogics. – 2025. – P. 62–67.
10. Kayumov O. A., Kayumova N. R.Development of a sign language recognition model for Uzbek words using deep learning methods // International Multidisciplinary Journal for Research & Development. – 2024.
11. Kayumov O. A., Kayumova N. R.Uzbek sign language classifier based on machine learning // European International Journal of Multidisciplinary Research and Management Studies. – 2024. – P. 269–280.
12. Kayumov O. A.Methodological basis of modeling the process of creating interactive intellectual electronic resources // Mental Enlightenment Scientific-Methodological Journal. – 2022. – P. 176–187.
